© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19799
    Prev
    Next
    INDEX
    Explanations

    integrated prevention, extensions, polyautoimmunity, roof, versatility, iot, immunopathology, co-occurrence, tower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĽĨä½ĵ
    -0.08
    éĽĨä½ĵçļĦ
    -0.08
     propag
    -0.07
    bage
    -0.07
    æķ´ä¸ªè¿ĩç¨ĭ
    -0.07
    éĽĨé«Ķ
    -0.07
    è¾ľ
    -0.07
    cxx
    -0.07
    æīĭæĬĬæīĭ
    -0.06
    ائØŃ
    -0.06
    POSITIVE LOGITS
    Cross
    0.11
    è·¨çķĮ
    0.11
     Cross
    0.11
    交åıī
    0.11
     cross
    0.11
    è·¨
    0.10
    综åIJĪæĢ§
    0.10
    ãĤ¯ãĥŃãĤ¹
    0.10
    èŀįéĢļ
    0.10
    -cross
    0.10
    Activations Density 0.171%

    No Known Activations